© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30620
    Prev
    Next
    INDEX
    Explanations

    determine (precision, diagnostic, outcomes)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berg
    -0.08
    缴æݥ被
    -0.07
    åĪ°è¾¾äºĨ
    -0.07
    ética
    -0.07
    és
    -0.07
    ай
    -0.07
    inct
    -0.07
    带åĬ¨äºĨ
    -0.07
    tring
    -0.07
    urement
    -0.07
    POSITIVE LOGITS
    ä¾Ŀæ³ķ追究责任
    0.07
    为éļ¾
    0.07
    éĢĤçĶ¨æ³ķå¾ĭ
    0.07
    è¿Ľè¡Į
    0.07
    æ±¹
    0.07
    åºĶçĶ¨æĬĢæľ¯
    0.07
    |int
    0.07
    ç®Ĺä»Ģä¹Ī
    0.07
    æıIJä¾Ľä¸Ģç§į
    0.06
     apply
    0.06
    Activations Density 0.115%

    No Known Activations